Run 4. Outer Step 65. Inner Step 52.

config.json

@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5649420,
-    5649449
+    5649478,
+    5649509
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 50,
+  "inner_step": 52,
   "inner_steps": 0,
   "last_allreduce_block": 5639485,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8d247c625ab0d99c1cd0f0b63fd03029d48d18751c4cbbda28e68fa907d199
+oid sha256:4dba2c78b7895f50c3af7f7c67df1793ceff32583f85704cee6776d22fb95b6e
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1121560c3a4b3a841ae6747c1a42d92f19d812af9ef86402993bdfc1c1a6a92c
+oid sha256:7260e53107879573c4ceb67498ede8f82895138eb0ab631368204fb201443b96
 size 4040701744